List your company

Constraint recall on Trip-planning windowed recall task

5Mean Constraints Recalledgpt-5-nano
-0.21.152.53.85Jul 6, 2026

Evaluation results

MethodLinks
gpt-5-nanoCondition=Notes2026.07555
gpt-5-miniCondition=Notes2026.07555
gpt-5Condition=Notes2026.07555
gpt-5.5Condition=Notes2026.07555
gpt-5-nanoCondition=Memory2026.074.845
gpt-5Condition=Memory2026.07435
gpt-5.5Condition=Memory2026.07435
gpt-5-miniCondition=Memory2026.073.635
gpt-5-nanoCondition=Baseline2026.07000
gpt-5-nanoCondition=Aware2026.07000
gpt-5-miniCondition=Baseline2026.07000
gpt-5-miniCondition=Aware2026.07000
gpt-5Condition=Baseline2026.07000
gpt-5Condition=Aware2026.07000
gpt-5.5Condition=Baseline2026.07000
gpt-5.5Condition=Aware2026.07000